First Principles Data Driven Potentials for Prediction of Iron Carbide Clusters

Iron carbide clusters are studied extensively in many catalysis fields by quantum chemistry methods. The high cost of structural energy calculation has always been the bottleneck of its development. First principles based on density functional theory (DFT) have high calculation accuracy and sound portability. Still, its computational cost is so high that it is difficult to carry out large-scale, long-term, and high-throughput simulations. A data driven potential is crucial for further accelerating the screening or prediction process in the high through-put calculation. In this paper, we generate 177k clusters data and choose some state-of-the-art machine learning models in physical chemistry to train them. The generated potential gives a very high prediction accuracy on the order of the structure stability and achieves better adaptability/tolerance on poor structures of clusters. In addition, we use the machine learning potential to assist in high-throughput data collection and realize the prediction of the adsorption position of hydrogen atoms on the cluster surface. We can get a more stable adsorption position of the hydrogen atom in a shorter time, compared with traditional quantum chemical calculators.